Statistical Learning Versus More Layers

STATISTICAL LEARNING Gentlemen, our learner verbalizes because the VC-Dimensions of our Kernel is too high. Get some experts and minimize the structural risk in a new one. Rework our loss function, make the next kernel stable, unbiased and consider using a soft margin NEURAL NETWORKS STACK MORE LAYERS LAYERS LAYERS If something simple like stacking more layers works better than statistical learning, then you have to wonder who the real clown is

A two-panel cartoon contrasts a serious statistical-learning presentation with a neural-network approach represented by a clown enthusiastically stacking more layers. The joke mocks the tendency to solve machine-learning problems by adding layers instead of carefully addressing theory, loss functions, kernels, and generalization. It is used as a sarcastic reaction to overcomplicated machine-learning research or simplistic deep-learning solutions.

• @profunctor_io / 6158 2021-01-18
• @dev_meme / 2689 2021-01-27